Email marketing platforms
Asked as “email marketing platform”, and as “email marketing tool”, on behalf of a mid-market B2B company. 45 first choices recorded across the direct, paraphrase, budget and scale prompts, twelve models each.
Gane, the publisher, sells software in this category. Every product here is measured by the same method as in every other category. How the conflict is handled.
Standing · first-choice share
40%
Contested · HubSpot Marketing Hub 27%
40ActiveCampaign27HubSpot Marketing Hub16Brevo18others
67% of first choices and every model's direct pick, at a 23% negative rate, just under the criticized line. Mailchimp is the most warned-against product here: half of its labels are negative.
By buyer segment
The same question asked on behalf of a different buyer. Each standing is computed within its segment; they sit side by side and are never added together.
The standing
Share is the count of first choices across the direct, paraphrase, budget and scale prompts, over all twelve models, for a mid-market B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrant
Show the eight products at 0%, ordered by negative rate
Bars are the share of first choices, 0 to 100Every product with at least 10 labels here. Every product name links to its product page.
All ten head-to-head pages: the top five products, each against each
Recommended versus criticized
Every product with at least 10 labels here, on both axes. The 30% line names a quadrant, not the verdict above: that one needs more than 40%.
Criticized challengerCriticized default
Negative label rate →
01
02
03
04
05
06
07
08
09
10
11
12
13Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative60%
Key
01ActiveCampaign40%
ActiveCampaign40%02HubSpot Marketing Hub27%
HubSpot Marketing Hub27%03Brevo16%
Brevo16%04Sender11%
Sender11%05MailerLite4%
MailerLite4%06Omnisend0%
Omnisend0%07Kit0%
Kit0%08EmailOctopus0%
EmailOctopus0%09Klaviyo0%
Klaviyo0%10GetResponse0%
GetResponse0%11Adobe Marketo Engage0%
Adobe Marketo Engage0%12Constant Contact0%
Constant Contact0%13Mailchimp0%
Mailchimp0%What they warned about
Five of twelve models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Gemini 3.5 Flash, Grok 4.20, DeepSeek V4 Flash, Llama 4 Maverick and MiniMax M2.5 changed. A high negative share on a product with few labels is a warning. A low share on a product with many labels is salience, not sentiment.
Mailchimp56%
27 of 48 labels negative · 11 of 12 models · 12 hard negative
“The Mailchimp / ActiveCampaign Trap: Mailchimp and ActiveCampaign are highly recognizable, but they are incredibly expensive for growing businesses.” Gemini 3.5 Flash, budget prompt
Constant Contact55%
12 of 22 labels negative · 9 of 12 models · 6 hard negative
“Users frequently criticize its interface as dated and clunky... often seen as a legacy choice rather than a modern growth tool.” Qwen 3.7 Flash, negative prompt
ActiveCampaign14%
8 of 56 labels negative · 7 of 12 models · 3 hard negative
“Avoid Mailchimp/ActiveCampaign/Constant Contact at larger list sizes” Qwen 3.7 Flash, budget prompt
AWeber75%
6 of 8 labels negative · 6 of 12 models · 5 hard negative
“Charges for unsubscribes/inactives (unfair billing flagged in analyses), lower deliverability... dated interface” Grok 4.20, negative prompt
What they cite
Four of the twelve models returned a source list in this edition: four return the pages they cited.
Sites the answers cite
17 of 72 answers in this category came back with a source list, from 4 of 12 models: citations where the model returns them, or the search results it consulted. 237 links across 87 sites, every framing counted. Ranked by the number of answers carrying the site or page. The other 8 models searched through a gateway that returned no source list on this edition.
11 answers · 17 citations · 3 models
vendor site · Mailtrap11 answers · 17 citations · 3 models
vendor site · Brevo9 answers · 10 citations · 3 models
8 answers · 10 citations · 3 models
8 answers · 9 citations · 3 models
vendor site · Constant Contact6 answers · 8 citations · 4 models
vendor site · Sequenzy6 answers · 6 citations · 3 models
vendor site · Sender5 answers · 6 citations · 3 models
vendor site · ActiveCampaign4 answers · 5 citations · 2 models
vendor site · InsiderOne4 answers · 4 citations · 3 models
vendor site · Klaviyo4 answers · 4 citations · 3 models
4 answers · 4 citations · 1 model
Pages the answers cite
The ten pages named in the most answers, by full address. A page here is one the models returned with a recommendation, not one the index endorses.
8 answers · 3 models
7 answers · 3 models
7 answers · 3 models
6 answers · 2 models
5 answers · 3 models
4 answers · 2 models
4 answers · 3 models
4 answers · 1 model
4 answers · 3 models
4 answers · 3 models
Search against answers
Each company's standing in the answers beside its site's footprint in Google search, one row a site: the products the models named on it with their shares, and the share they add up to; monthly searches on Google, and DataForSEO's estimate of AI search demand (modeled from search signals, directional, not a count of queries to any assistant), for the most-searched of the company's and its products' names (the name is in each row's hover text); estimated monthly organic visits to the site; and its best position in Google's top ten for “best email marketing platform”, “email marketing platform”. US estimates from DataForSEO and Google's Ads Transparency Center. A small company's site, or a mid-sized company's site for its flagship, is marked company; a product on a large parent's site (Google, Microsoft) has no site figures. A column with no figures for this category is left out, and an empty cell means none were seen, not none exist. Two measurements side by side: neither is read as the cause of the other.
| Company and products | Share | Own site cited | Name searches, Google | AI search demand, est. | Organic visits | Paid search a month, est. | Google ads, last 30 days | Best Google position |
|---|---|---|---|---|---|---|---|---|
| ActiveCampaign activecampaign.com | 40% | 437 | 18,100 | 307 | 235,709 | $1,424 | 32 | |
| HubSpot parent site HubSpot Marketing Hub 27% | 27% | 991 | 368,000 | 9,776 | ||||
| Brevo brevo.com | 16% | 440 | 40,500 | 327 | 81,741 | $17,847 | 106 | 9 |
| Sender sender.net | 11% | 75 | 9,900 | 10,349 | 69,078 | 13 | ||
| MailerLite mailerlite.com | 4% | 150 | 49,500 | 311 | 59,716 | $85 | 115 | 7 |
| Sequenzy sequenzy.com | 2% | 7 | ||||||
| Omnisend omnisend.com | 0% | 199 | 9,900 | 108 | 51,545 | $113 | 66 | |
| Kit kit.com | 0% | 42 | 90,500 | 355,784 | 208,645 | $10 | 98 | |
| EmailOctopus emailoctopus.com | 0% | 24 | 2,400 | 33 | 19,496 | 38 | ||
| Moosend moosend.com | 0% | 30 | 1,900 | 19 | 71,515 | 2 |
Google's top ten for the two searches hold 11 sites; 6 of them are among the sites the models cited here (brevo.com, constantcontact.com, emailtooltester.com, emailvendorselection.com, mailtrap.io, ventureharbour.com). The first result for “best email marketing platform” is emailvendorselection.com.
How they answered
Six framings of the same buying question, each sent to every model in a fresh session with search on. One row per model, so a row shows whether it held its answer under rewording, what it named when cost was the constraint, and what it argued against. Computed from the raw judge labels.ShowHide
How they answered
Six framings of the same buying question, each sent to every model in a fresh session with search on. One row per model, so a row shows whether it held its answer under rewording, what it named when cost was the constraint, and what it argued against. Computed from the raw judge labels.
ShowHideModelDirect“What is the best email marketing platform for a mid-market B2B company?”Paraphrase“Which email marketing tool would you recommend to a mid-sized B2B company?”Comparative“What are the top email marketing platforms and how do they differ?”Budget-constrained“What is the best email marketing platform for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating an email marketing platform. What should we look at?”Negative“Which email marketing platforms should I avoid or be cautious about?”
Claude Haiku 4.5HubSpot Marketing Hubno first choiceChangedagainst: Klaviyono first choiceBrevono first choiceagainst: ActiveCampaign
One alternative
ActiveCampaignFive alternatives
ActiveCampaign, Constant Contact, Klaviyo, Mailchimp, MailerLiteThree alternatives
Kit, MailerLite, OmnisendGPT-5.4 miniActiveCampaignagainst: MailchimpHubSpot Marketing HubChangedagainst: Adobe Marketo Engage, Klaviyo, Mailchimpno first choiceBrevo, MailerLiteagainst: Constant Contact, Mailchimpno first choicenothing named
Two alternatives
Braze, HubSpot Marketing HubOne alternative
ActiveCampaignGemini 3.5 FlashActiveCampaignHubSpot Marketing HubChangedMailerLiteagainst: MailchimpSenderagainst: ActiveCampaign, Flodesk, Mailchimp, MailerLiteno first choiceagainst: Adobe Marketo Engage, Mailchimp, MailerLite, Salesforce Marketing Cloudagainst: AWeber, Constant Contact, HubSpot Marketing Hub, MailWizz, Mailchimp, Mautic, Salesforce Marketing Cloud, Sendy
Three alternatives
Brevo, HubSpot Marketing Hub, Salesforce Marketing Cloud Account EngagementThree alternatives
ActiveCampaign, Brevo, Salesforce Marketing Cloud Account EngagementSeven alternatives
ActiveCampaign, Beehiiv, Brevo, HubSpot Marketing Hub, Kit, Klaviyo, OmnisendThree alternatives
Beehiiv, Brevo, EmailOctopusEight alternatives
ActiveCampaign, Braze, Customer.io, HubSpot Marketing Hub, Insider, Iterable, Klaviyo, Salesforce Marketing Cloud Account EngagementPerplexity SonarHubSpot Marketing Hubagainst: Adobe Marketo EngageHubSpot Marketing HubHeldno first choiceBrevono first choiceagainst: AWeber, ActiveCampaign, Constant Contact, HubSpot Marketing Hub, Mailchimp
One alternative
ActiveCampaignFive alternatives
ActiveCampaign, Brevo, Mailchimp, MailerLite, ZoomInfo MarketingEight alternatives
ActiveCampaign, Brevo, HubSpot Marketing Hub, Kit, Klaviyo, Mailchimp, MailerLite, OmnisendThree alternatives
MailerLite, Sender, Zoho CampaignsGrok 4.20ActiveCampaign, HubSpot Marketing Hubagainst: KlaviyoActiveCampaignChangedagainst: Mailchimpno first choiceSenderagainst: MailerLiteActiveCampaign, Brevoagainst: AWeber, Benchmark Email, Brevo, GetResponse, Klaviyo, Mailchimp
Two alternatives
Adobe Marketo Engage, BrevoOne alternative
HubSpot Marketing HubTwo alternatives
Brevo, EmailOctopusThree alternatives
HubSpot Marketing Hub, Klaviyo, Salesforce Marketing CloudMistral SmallActiveCampaignagainst: Salesforce Marketing CloudActiveCampaignHeldHiMail.aiSenderno first choiceagainst: Constant Contact, Mailchimp
Two alternatives
Brevo, HubSpot Marketing HubTwo alternatives
HubSpot Marketing Hub, Salesforce Marketing Cloud Account EngagementNine alternatives
ActiveCampaign, Beehiiv, Brevo, Constant Contact, HubSpot Marketing Hub, Kit, Klaviyo, MailerLite, MoosendTwo alternatives
Brevo, MailerLiteDeepSeek V4 FlashActiveCampaignagainst: Adobe Marketo Engage, Salesforce Marketing Cloud Account EngagementHubSpot Marketing HubChangedagainst: Adobe Marketo Engage, Klaviyo, Salesforce Marketing Cloud Account Engagementno first choiceBrevoagainst: ActiveCampaign, Constant Contact, MailchimpActiveCampaign, HubSpot Marketing Hubagainst: Klaviyo, Mailchimpagainst: AWeber, ActiveCampaign, Benchmark Email, Brevo, Constant Contact, Klaviyo, Mailchimp, Mailjet, SendGrid, SendMails, SimplyCast
One alternative
HubSpot Marketing HubTwo alternatives
ActiveCampaign, BrevoTen alternatives
ActiveCampaign, Brevo, Constant Contact, GetResponse, HubSpot Marketing Hub, Kit, Klaviyo, Mailchimp, MailerLite, OmnisendFour alternatives
EmailOctopus, MailerLite, Sender, Zoho CampaignsTwo alternatives
Brevo, Customer.ioLlama 4 MaverickActiveCampaign, HubSpot Marketing HubActiveCampaignChangedno first choiceSequenzyno first choiceagainst: ActiveCampaign, Constant Contact, GetResponse, HubSpot Marketing Hub, Mailchimp
Two alternatives
Mailchimp, OmnisendTwo alternatives
Brevo, EmailOctopusQwen 3.7 FlashHubSpot Marketing HubHubSpot Marketing HubHeldagainst: Adobe Marketo Engage, MailchimpKlaviyoagainst: HubSpot Marketing HubBrevo, MailerLiteagainst: ActiveCampaign, Constant Contact, MailchimpActiveCampaignagainst: Mailchimpagainst: Constant Contact, GetResponse, HubSpot Marketing Hub, Klaviyo, Mailchimp, Zoho Campaigns
Two alternatives
ActiveCampaign, Customer.ioOne alternative
ActiveCampaignSix alternatives
ActiveCampaign, Beehiiv, Brevo, Kit, Mailchimp, OmnisendFour alternatives
EmailOctopus, Flodesk, Sender, Zoho CampaignsTwo alternatives
HubSpot Marketing Hub, KlaviyoKimi K2ActiveCampaignagainst: Adobe Marketo EngageActiveCampaignHeldActiveCampaign, Omnisendagainst: HubSpot Marketing Hub, Klaviyo, MailchimpSenderagainst: MailchimpActiveCampaignagainst: Constant Contact, Mailchimpagainst: AWeber, ActiveCampaign, Benchmark Email, Campaigner, Constant Contact, Drip, Email Octopus, GetResponse, HubSpot Marketing Hub, Kit, Klaviyo, Mailchimp, Mailjet, Mailmodo, SendGrid
One alternative
HubSpot Marketing HubTwo alternatives
HubSpot Marketing Hub, Salesforce Marketing Cloud Account EngagementSix alternatives
Beehiiv, Brevo, GetResponse, Kit, MailerLite, SenderThree alternatives
Brevo, MailerLite, MoosendFour alternatives
Brevo, Campaign Monitor, HubSpot Marketing Hub, KlaviyoGLM 4.7 FlashXActiveCampaignActiveCampaignHeldBrevoBrevoagainst: Mailchimpno first choiceagainst: Benchmark Email, Constant Contact, GetResponse, Mailchimp
Three alternatives
Brevo, HubSpot Marketing Hub, KlaviyoTwo alternatives
HubSpot Marketing Hub, MailchimpEight alternatives
ActiveCampaign, HubSpot Marketing Hub, Kit, Klaviyo, Mailchimp, Moosend, Omnisend, SenderThree alternatives
MailerLite, Moosend, SenderMiniMax M2.5ActiveCampaignHubSpot Marketing HubChangedagainst: Mailchimpno first choiceSenderno first choiceagainst: AWeber, Drip, Mailchimp, Mailmodo
Two alternatives
Adobe Marketo Engage, HubSpot Marketing HubOne alternative
ActiveCampaignThree alternatives
Brevo, EmailOctopus, Mailtrap Email MarketingBold is the first choiceAlternatives are counted; the count opens them.What the answer argued against
The record
One row per call: the version string exactly as returned, whether the model searched, sources cited, and latency.
Seventy-two rows: every prompt, every model, every answer.
| Prompt | Model | Version string | Time (UTC) | Searched | Sources | Latency |
|---|---|---|---|---|---|---|
| Direct recommendation | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 00:39 | yes | 7 | 6 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-15 00:01 | yes | 4 | 8 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 03:11 | yes | 11 | 18 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-09-15 04:34 | yes | 20 | 4 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-15 02:29 | yes | 0 | 8 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-09-14 22:56 | yes | 0 | 10 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-15 01:18 | yes | 0 | 28 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-14 23:11 | yes | 0 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 03:10 | yes | 0 | 54 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 04:23 | yes | 0 | 32 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 03:06 | yes | 0 | 28 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 03:45 | yes | 0 | 16 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-14 23:00 | no | 0 | 5 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-15 03:37 | no | 0 | 3 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 01:30 | no | 0 | 10 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-09-15 04:43 | yes | 20 | 5 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-14 23:23 | yes | 0 | 7 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 04:02 | yes | 0 | 8 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-14 23:53 | yes | 0 | 41 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 02:28 | yes | 0 | 1 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 00:27 | yes | 0 | 37 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 02:17 | yes | 0 | 34 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 02:41 | yes | 0 | 17 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 05:02 | yes | 0 | 14 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 00:30 | yes | 7 | 8 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-14 23:10 | yes | 6 | 8 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 04:03 | yes | 12 | 23 s |
| Comparative | Perplexity Sonar | sonar | 2026-09-15 04:28 | yes | 20 | 7 s |
| Comparative | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-15 02:18 | yes | 0 | 14 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 01:11 | yes | 0 | 7 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-15 01:51 | yes | 0 | 126 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 03:21 | yes | 0 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-14 23:54 | no | 0 | 31 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 01:24 | yes | 0 | 47 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-14 22:56 | yes | 0 | 16 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 04:24 | no | 0 | 12 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 00:11 | yes | 8 | 7 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-15 02:19 | yes | 4 | 4 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 00:54 | yes | 22 | 23 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-09-15 01:54 | yes | 20 | 5 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-15 01:38 | yes | 0 | 6 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 00:02 | yes | 0 | 6 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-14 23:26 | yes | 0 | 21 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 01:22 | yes | 0 | 1 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 03:27 | yes | 0 | 31 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 02:15 | yes | 0 | 13 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 03:48 | yes | 0 | 12 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 03:14 | yes | 0 | 13 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 03:09 | no | 0 | 5 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-15 03:54 | no | 0 | 8 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-15 02:47 | no | 0 | 16 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-09-15 03:20 | yes | 20 | 6 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-15 00:28 | yes | 0 | 8 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-09-15 00:08 | no | 0 | 6 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-14 23:26 | yes | 0 | 57 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-14 23:03 | yes | 0 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 00:51 | no | 0 | 40 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 00:44 | yes | 0 | 25 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 01:13 | no | 0 | 11 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 00:08 | no | 0 | 9 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-09-15 04:07 | yes | 19 | 7 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-09-15 02:25 | no | 0 | 4 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-09-14 23:21 | yes | 17 | 29 s |
| Negative framing | Perplexity Sonar | sonar | 2026-09-15 00:32 | yes | 20 | 6 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.1-fast-non-reasoning via vertex (asked for grok-4.20-non-reasoning; the API answered as this version) | 2026-09-15 05:00 | yes | 0 | 7 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-09-14 23:53 | yes | 0 | 10 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-09-15 00:52 | yes | 0 | 59 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-09-15 04:08 | yes | 0 | 1 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-09-15 04:37 | yes | 0 | 45 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-09-15 02:35 | yes | 0 | 51 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-09-15 01:28 | yes | 0 | 19 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-09-15 00:56 | yes | 0 | 11 s |
Noise floor in this category
Flips between the edition run and its calibration repeat. Six prompts per model is a small sample; the index-wide floor is the number to trust.
ShowHide
Claude Haiku 4.5
3 of 4 flipped
GPT-5.4 mini
2 of 3 flipped
Gemini 3.5 Flash
4 of 5 flipped
Perplexity Sonar
0 of 3 flipped
Grok 4.20
1 of 5 flipped
Mistral Small
2 of 5 flipped
DeepSeek V4 Flash
4 of 5 flipped
Llama 4 Maverick
2 of 3 flipped
Qwen 3.7 Flash
4 of 6 flipped
Kimi K2
5 of 6 flipped
GLM 4.7 FlashX
3 of 5 flipped
MiniMax M2.5
4 of 6 flipped
Normalization in this category
Every judgment call made between the raw labels and the numbers above, listed so it is visible and reversible.
ShowHide
Category-scoped readings
HubSpot read as HubSpot Marketing Hub
Salesforce read as Salesforce Marketing Cloud
Unresolved, counted raw
MailWizz
SendGrid Transactional
Sendy
SimplyCast
Discontinued, still offered
No shut-down product was recommended here.